Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5245 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1597. Min Range: -2.1597

Max Act: 2.1597. Min Act: -0.0001

Data Index: 1561528 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.9335. Min Act: -0.0001

Data Index: 1473521 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1443485 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.8992. Min Act: -0.0000

Data Index: 1461682 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.7204. Min Act: -0.0000

Data Index: 1529988 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1632683 (Python Code)

Max Activating Token Index: 277

Text #6

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1424659 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.8392. Min Act: -0.0000

Data Index: 1434632 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.7156. Min Act: -0.0001

Data Index: 1419792 (Python Code)

Max Activating Token Index: 280

Text #9

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.7069. Min Act: -0.0000

Data Index: 1572039 (Python Code)

Max Activating Token Index: 170

Text #10

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.6767. Min Act: -0.0000

Data Index: 1653273 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.6059. Min Act: -0.0001

Data Index: 1418118 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.5288. Min Act: -0.0001

Data Index: 1623827 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.6074. Min Act: -0.0000

Data Index: 1392715 (Python Code)

Max Activating Token Index: 459

Text #14

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1478342 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1511208 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.5017. Min Act: -0.0000

Data Index: 1614892 (Python Code)

Max Activating Token Index: 571

Text #17

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.5045. Min Act: -0.0000

Data Index: 1563102 (Python Code)

Max Activating Token Index: 649

Text #18

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1571519 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 2.1597. Min Range: -2.1597

Max Act: 1.5095. Min Act: -0.0001

Data Index: 1510202 (Python Code)

Max Activating Token Index: 650